4 papers · 1 filter
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
Ignacio D. Lopez-Miguel, Ezio Bartocci, Thomas Eiter +1
Explainability remains a key issue in reinforcement learning (RL). Distilling an interpretable policy from an agent trained in a complex environment is particularly challenging whe…
Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
Mihaela-Larisa Clement, Mónika Farsang, Agnes Poks +4
The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on…
Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs
Andrey Kofnov, Daniel Kapla, Ezio Bartocci +1
We derive exact upper and lower bounds for the cumulative distribution function (cdf) of the output of a neural network (NN) over its entire support subject to noisy (stochastic) i…
Rule-Guided Reinforcement Learning Policy Evaluation and Improvement
Martin Tappler, Ignacio D. Lopez-Miguel, Sebastian Tschiatschek +1
We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-…